Agent skill
dspy-optimization-not-improving
Sub-skill of dspy: Optimization Not Improving (+2).
Install this agent skill to your Project
npx add-skill https://github.com/vamseeachanta/workspace-hub/tree/main/.claude/skills/_archive/ai/prompting/dspy/optimization-not-improving
SKILL.md
Optimization Not Improving (+2)
Optimization Not Improving
# Increase number of training examples
# Ensure diverse, high-quality examples
# Try different optimizer settings
optimizer = BootstrapFewShotWithRandomSearch(
metric=metric,
max_bootstrapped_demos=8, # Increase
num_candidate_programs=20, # More search
num_threads=8
)
Module Too Slow
# Use faster model for compilation
compile_lm = dspy.OpenAI(model="gpt-4.1-mini")
deploy_lm = dspy.OpenAI(model="gpt-4")
with dspy.settings.context(lm=compile_lm):
optimized = optimizer.compile(module, trainset=data)
# Deploy with stronger model
dspy.settings.configure(lm=deploy_lm)
Out of Memory
# Process in batches
batch_size = 10
for i in range(0, len(trainset), batch_size):
batch = trainset[i:i+batch_size]
process_batch(batch)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
vamseeachanta/workspace-hub
gsd-complete-milestone
Archive completed milestone and prepare for next version
vamseeachanta/workspace-hub
gsd-reapply-patches
Reapply local modifications after a GSD update
vamseeachanta/workspace-hub
gsd-verify-work
Validate built features through conversational UAT
vamseeachanta/workspace-hub
gsd-thread
Manage persistent context threads for cross-session work
vamseeachanta/workspace-hub
clinical-trial-protocol
Generate clinical trial protocols for medical devices or drugs through a modular, waypoint-based architecture with research-only and full protocol modes.
vamseeachanta/workspace-hub
single-cell-rna-qc
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations.
Didn't find tool you were looking for?